ibivibiv commited on
Commit
44d513b
1 Parent(s): 9a4c0f3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -48,7 +48,9 @@ text = tokenizer.batch_decode(outputs)[0]
48
  print(text)
49
  ```
50
 
 
51
 
 
52
  @misc{open-llm-leaderboard,
53
  author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
54
  title = {Open LLM Leaderboard},
@@ -56,6 +58,8 @@ print(text)
56
  publisher = {Hugging Face},
57
  howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
58
  }
 
 
59
  @software{eval-harness,
60
  author = {Gao, Leo and
61
  Tow, Jonathan and
@@ -82,6 +86,8 @@ print(text)
82
  doi = {10.5281/zenodo.5371628},
83
  url = {https://doi.org/10.5281/zenodo.5371628}
84
  }
 
 
85
  @misc{clark2018think,
86
  title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
87
  author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
@@ -90,6 +96,8 @@ print(text)
90
  archivePrefix={arXiv},
91
  primaryClass={cs.AI}
92
  }
 
 
93
  @misc{zellers2019hellaswag,
94
  title={HellaSwag: Can a Machine Really Finish Your Sentence?},
95
  author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
@@ -98,6 +106,8 @@ print(text)
98
  archivePrefix={arXiv},
99
  primaryClass={cs.CL}
100
  }
 
 
101
  @misc{hendrycks2021measuring,
102
  title={Measuring Massive Multitask Language Understanding},
103
  author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
@@ -106,6 +116,8 @@ print(text)
106
  archivePrefix={arXiv},
107
  primaryClass={cs.CY}
108
  }
 
 
109
  @misc{lin2022truthfulqa,
110
  title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
111
  author={Stephanie Lin and Jacob Hilton and Owain Evans},
@@ -114,6 +126,8 @@ print(text)
114
  archivePrefix={arXiv},
115
  primaryClass={cs.CL}
116
  }
 
 
117
  @misc{DBLP:journals/corr/abs-1907-10641,
118
  title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
119
  author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
@@ -122,6 +136,8 @@ print(text)
122
  archivePrefix={arXiv},
123
  primaryClass={cs.CL}
124
  }
 
 
125
  @misc{DBLP:journals/corr/abs-2110-14168,
126
  title={Training Verifiers to Solve Math Word Problems},
127
  author={Karl Cobbe and
@@ -141,4 +157,5 @@ print(text)
141
  archivePrefix={arXiv},
142
  primaryClass={cs.CL}
143
  }
 
144
 
 
48
  print(text)
49
  ```
50
 
51
+ ## Citations
52
 
53
+ ```
54
  @misc{open-llm-leaderboard,
55
  author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
56
  title = {Open LLM Leaderboard},
 
58
  publisher = {Hugging Face},
59
  howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
60
  }
61
+ ```
62
+ ```
63
  @software{eval-harness,
64
  author = {Gao, Leo and
65
  Tow, Jonathan and
 
86
  doi = {10.5281/zenodo.5371628},
87
  url = {https://doi.org/10.5281/zenodo.5371628}
88
  }
89
+ ```
90
+ ```
91
  @misc{clark2018think,
92
  title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
93
  author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
 
96
  archivePrefix={arXiv},
97
  primaryClass={cs.AI}
98
  }
99
+ ```
100
+ ```
101
  @misc{zellers2019hellaswag,
102
  title={HellaSwag: Can a Machine Really Finish Your Sentence?},
103
  author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
 
106
  archivePrefix={arXiv},
107
  primaryClass={cs.CL}
108
  }
109
+ ```
110
+ ```
111
  @misc{hendrycks2021measuring,
112
  title={Measuring Massive Multitask Language Understanding},
113
  author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
 
116
  archivePrefix={arXiv},
117
  primaryClass={cs.CY}
118
  }
119
+ ```
120
+ ```
121
  @misc{lin2022truthfulqa,
122
  title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
123
  author={Stephanie Lin and Jacob Hilton and Owain Evans},
 
126
  archivePrefix={arXiv},
127
  primaryClass={cs.CL}
128
  }
129
+ ```
130
+ ```
131
  @misc{DBLP:journals/corr/abs-1907-10641,
132
  title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
133
  author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
 
136
  archivePrefix={arXiv},
137
  primaryClass={cs.CL}
138
  }
139
+ ```
140
+ ```
141
  @misc{DBLP:journals/corr/abs-2110-14168,
142
  title={Training Verifiers to Solve Math Word Problems},
143
  author={Karl Cobbe and
 
157
  archivePrefix={arXiv},
158
  primaryClass={cs.CL}
159
  }
160
+ ```
161